Synthesis‑Aware ML Scientist (Drug Discovery)

Genentech; New York (NY); On-site; USD 141,000 - 262,000; Full time

Benefits offered by this job

Discretionary annual bonus

Job summary

Genentech in New York City seeks a Machine Learning Scientist to drive synthesis-aware molecular design within AI for Drug Discovery. You will build ML methods for retrosynthesis, generation, and optimization, integrating proprietary data to create scalable, chemistries-aware workflows.

The role requires a PhD or equivalent, deep ML expertise (GNNs, RL, PyTorch/JAX), and fluency with cheminformatics tools such as RDKit.

Qualifications

• PhD or equivalent research depth in ML, computational chemistry, chemical engineering or related quantitative field.
• Up to 2 years of industry research experience (Scientist) or 2+ years (Senior Scientist).
• Proven publications or public portfolio of projects.

Responsibilities

• Develop ML methods for synthesis-aware molecular design across retrosynthesis, synthesis planning, molecular generation, and search in synthesizable chemical spaces.
• Integrate proprietary reaction and biochemical data to design next-gen synthesis-aware models and workflows.
• Build robust pipelines for active-learning loops interfacing with automated synthesis platforms.
• Design novel batch synthesis-planning algorithms to maximize chemical-space coverage and efficiency.
• Publish, open-source releases, and present at conferences; collaborate with Roche Genentech researchers and academic partners.

Skills

Machine learning

Linear algebra

Probability

Optimization

Graph neural networks

Sequence models

Reinforcement learning

Python

PyTorch

JAX

Scientific software development

Education

PhD or equivalent

Tools

RDKit

OpenEye

Job description

Genentech in New York City seeks a Machine Learning Scientist to drive synthesis-aware molecular design within AI for Drug Discovery. You will build ML methods for retrosynthesis, generation, and optimization, integrating proprietary data to create scalable, chemistries-aware workflows.

The role requires a PhD or equivalent, deep ML expertise (GNNs, RL, PyTorch/JAX), and fluency with cheminformatics tools such as RDKit.